2 code implementations • 22 Jun 2022 • Rajat Talak, Lisa Peng, Luca Carlone
Our third contribution is a novel self-supervised training approach that uses our certificate of observable correctness to provide the supervisory signal to C-3PO during training.
1 code implementation • 2 Aug 2021 • Zachary Ravichandran, Lisa Peng, Nathan Hughes, J. Daniel Griffith, Luca Carlone
In this work, we present a reinforcement learning framework that leverages high-level hierarchical representations to learn navigation policies.
no code implementations • NeurIPS 2021 • Rajat Talak, Siyi Hu, Lisa Peng, Luca Carlone
We also prove that the number of parameters needed to achieve an $\epsilon$-approximation of the distribution function is exponential in the treewidth of the input graph, but linear in its size.